Nikolay Gospodinov

Commodity Prices, Convenience Yields, and Inflation

This paper provides evidence that the two leading principal components in a panel of 23 commodity convenience yields have statistically and quantitatively important predictive power for inflation even after controlling for unemployment gap and oil prices. The results hold up in out-of-sample forecasts, across forecast horizons, and across G7 countries. The convenience yields also explain commodity prices and can be seen as informational variables about future economic conditions as conveyed by the futures markets. A bootstrap procedure for conducting inference when the principal components are used as regressors is also proposed.

Modeling Financial Return Dynamics via Decomposition

While the predictability of excess stock returns is detected by traditional predictive regressions as statistically small, the direction-of-change and volatility of returns exhibit a substantially larger degree of dependence over time. We capitalize on this observation and decompose the returns into a product of sign and absolute value components whose joint distribution is obtained by combining a multiplicative error model for absolute values, a dynamic binary choice model for signs, and a copula for their interaction. Our decomposition model is able to incorporate important nonlinearities in excess return dynamics that cannot be captured in the standard predictive regression setup. The empirical analysis of U.S. stock return data shows statistically and economically significant forecasting gains of the decomposition model over the conventional predictive regression.

Misspecification-Robust Inference in Linear Asset-Pricing Models with Irrelevant Risk Factors

We show that in misspecified models with useless factors (for example, factors that are independent of the returns on the test assets), the standard inference procedures tend to erroneously conclude, with high probability, that these irrelevant factors are priced and the restrictions of the model hold. Our proposed model selection procedure, which is robust to useless factors and potential model misspecification, restores the standard inference and proves to be effective in eliminating factors that do not improve the models pricing ability. The practical relevance of our analysis is illustrated using simulations and empirical applications.

SPECIFICATION TESTING IN MODELS WITH MANY INSTRUMENTS

This paper studies the asymptotic validity of the Anderson-Rubin (AR) test and the J test of overidentifying restrictions in linear models with many instruments. When the number of instruments increases at the same rate as the sample size, we establish that the conventional AR and J tests are asymptotically incorrect. Some versions of these tests, that are developed for situations with moderately many instruments, are also shown to be asymptotically invalid in this framework. We propose modifications of the AR and J tests that deliver asymptotically correct sizes. Importantly, the corrected tests are robust to the numerosity of the moment conditions in the sense that they are valid for both few and many instruments. The simulation results illustrate the excellent properties of the proposed tests.

Global Health Warnings on Tobacco Packaging: Evidence from the Canadian Experiment

Abstract New health warnings on tobacco packaging in Canada became mandatory in January 2001. As of that time producers were required to print large-font warning text and graphic images describing the health consequences of using tobacco. This study uses micro data from two waves of Health Canadas Canadian Tobacco Use Monitoring Surveys bordering the legislation to investigate if the introduction of the warnings had any significant impacts on smokers. The recently drafted Framework Convention on Tobacco Control, under the sponsorship of the World Health Assembly, assigns a central role for this type of message. Our findings indicate that the warnings have not had a discernible impact on smoking prevalence. The evidence of their impact on quantity smoked is positive, though only at a relatively low level of confidence.

Inference in Nearly Nonstationary SVAR Models With Long-Run Identifying Restrictions

This paper considers inference for impulse responses in models with highly persistent variables. We show that the impulse responses of interest are not consistently estimable under the long-run identification scheme when the strongly dependent process is parameterized as local to unity. We employ the instrumental variable framework to argue that the inconsistency and the large sampling uncertainty associated with the impulse responses arise from a weak instrument problem. Furthermore, the structure of the model is used to impose additional statistical restrictions that are combined with the economic long-run, identifying constraints to obtain an improved estimator.

Median unbiased forecasts for highly persistent autoregressive processes

This paper considers the construction of median unbiased forecasts for near-integrated AR( p ) processes. It is well known that the OLS estimation in AR models produces downward biased parameter estimates. When the largest AR root is near unity, the multi-step forecast iteration leads to severe underprediction of the future value of the conditional mean. The paper derives the appropriately scaled limiting representation of the deviation of the forecast value from the true conditional mean. The asymmetry of this asymptotic representation suggests that the median unbiasedness would be a better criterion in evaluating the properties of the forecast point estimates. Furthermore, the dependence of the limiting distribution on the local-to-unity parameter precludes the use of the standard asymptotic and bootstrap methods for correcting for the bias. For this purpose, we develop a computationally convenient method that generates bootstrap samples backward in time (conditional on the last p observations) and approximates the median function of the predictive distribution on a grid of strategically chosen points around the OLS forecast. Inverting this median function yields median unbiased forecasts. The numerical results demonstrate the impartiality property of the grid MU forecasts and their good accuracy in comparison to several widely used forecasting techniques.

Sensitivity of Impulse Responses to Small Low-Frequency Comovements: Reconciling the Evidence on the Effects of Technology Shocks

This article clarifies the empirical source of the debate on the effect of technology shocks on hours worked. We find that the contrasting conclusions from levels and differenced vector autoregression specifications, documented in the literature, can be explained by a small low-frequency comovement between hours worked and productivity growth that gives rise to a discontinuity in the solution for the structural coefficients identified by long-run restrictions. Whereas the low-frequency comovement is allowed for in the levels specification, it is implicitly set to 0 in the differenced vector autoregression. Consequently, even when the root of hours is very close to 1 and the low-frequency comovement is quite small, removing it can give rise to biases of sufficient size to account for the empirical difference between the two specifications.

On the Hansen-Jagannathan distance with a no-arbitrage constraint

We provide an in-depth analysis of the theoretical and statistical properties of the Hansen-Jagannathan (HJ) distance that incorporates a no-arbitrage constraint. We show that for stochastic discount factors (SDF) that are spanned by the returns on the test assets, testing the equality of HJ distances with no-arbitrage constraints is the same as testing the equality of HJ distances without no-arbitrage constraints. A discrepancy can exist only when at least one SDF is a function of factors that are poorly mimicked by the returns on the test assets. Under a joint normality assumption on the SDF and the returns, we derive explicit solutions for the HJ distance with a no-arbitrage constraint, the associated Lagrange multipliers, and the SDF parameters in the case of linear SDFs. This solution allows us to show that nontrivial differences between HJ distances with and without no-arbitrage constraints can arise only when the volatility of the unspanned component of an SDF is large and the Sharpe ratio of the tangency portfolio of the test assets is very high. Finally, we present the appropriate limiting theory for estimation, testing, and comparison of SDFs using the HJ distance with a no-arbitrage constraint.

Unit Roots, Cointegration, and Pretesting in Var Models ☆ ☆The views expressed here are the authors and not necessarily those of the Federal Reserve Bank of Atlanta or the Federal Reserve System.

Abstract This article investigates the robustness of impulse response estimators to near unit roots and near cointegration in vector autoregressive (VAR) models. We compare estimators based on VAR specifications determined by pretests for unit roots and cointegration as well as unrestricted VAR specifications in levels. Our main finding is that the impulse response estimators obtained from the levels specification tend to be most robust when the magnitude of the roots is not known. The pretest specification works well only when the restrictions imposed by the model are satisfied. Its performance deteriorates even for small deviations from the exact unit root for one or more model variables. We illustrate the practical relevance of our results through simulation examples and an empirical application.